Constrained Deep Transfer Feature Learning and its Applications

TL;DR

This paper introduces a constrained deep transfer feature learning method that iteratively improves transfer learning by incorporating target domain constraints, demonstrated on eye detection and facial expression recognition tasks.

Contribution

It proposes a novel iterative transfer learning approach with domain-specific constraints to enhance feature transfer in deep models.

Findings

Effective transfer of features from visible to thermal domain for eye detection.

Improved cross-view facial expression recognition performance.

Demonstrated superiority over existing transfer learning methods.

Abstract

Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from the source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as a constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.